Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 520 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.2222. Min Act: -0.1700
Data Index: 1178508 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.1909. Min Act: -0.1700
Data Index: 7125324 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.1909. Min Act: -0.1700
Data Index: 7214317 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.1284. Min Act: -0.1700
Data Index: 3049526 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0972. Min Act: -0.1700
Data Index: 5927099 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0659. Min Act: -0.1700
Data Index: 7531871 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0659. Min Act: -0.1700
Data Index: 896984 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 2674289 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 1113152 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 3499901 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 1991960 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 3642191 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 6613526 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 3302374 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0346. Min Act: -0.1700
Data Index: 2115019 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0034. Min Act: -0.1700
Data Index: 1766003 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0034. Min Act: -0.1700
Data Index: 4238939 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0034. Min Act: -0.1700
Data Index: 6410640 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0034. Min Act: -0.1700
Data Index: 1012468 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2222. Min Range: -4.2222
Max Act: 4.0034. Min Act: -0.1700
Data Index: 5572468 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19